Superkernel Neural Architecture Search for Image Denoising
This work addresses the time-consuming training issue in NAS for image enhancement, which is a problem for researchers and practitioners in computer vision.
The paper tackled the problem of slow Neural Architecture Search (NAS) for image denoising by introducing an efficient superkernel technique, achieving training times of 6-8 GPU hours on the SIDD+ benchmark.
Recent advancements in Neural Architecture Search(NAS) resulted in finding new state-of-the-art Artificial Neural Network (ANN) solutions for tasks like image classification, object detection, or semantic segmentation without substantial human supervision. In this paper, we focus on exploring NAS for a dense prediction task that is image denoising. Due to a costly training procedure, most NAS solutions for image enhancement rely on reinforcement learning or evolutionary algorithm exploration, which usually take weeks (or even months) to train. Therefore, we introduce a new efficient implementation of various superkernel techniques that enable fast (6-8 RTX2080 GPU hours) single-shot training of models for dense predictions. We demonstrate the effectiveness of our method on the SIDD+ benchmark for image denoising.